© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 29813
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Steve" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.22
    1.2%
    385
    +0.14
    0.8%
    410
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.22
    0.03
    211
    +0.14
    0.02
    251
    +0.14
    0.03
    Negative Logits
    ĥ½
    -3.24
    ĨĴ
    -3.07
    Ļª
    -3.07
    ¿½
    -2.99
    °
    -2.68
    ·¸
    -2.65
    į
    -2.60
    ĺ
    -2.59
    Ķ
    -2.51
    Ĥ
    -2.50
    POSITIVE LOGITS
    pson
    1.89
     Jobs
    1.64
     Forbes
    1.63
     Miller
    1.57
     Smith
    1.53
    ius
    1.51
     Temple
    1.50
    iej
    1.49
     Kennedy
    1.49
    aling
    1.48
    Activations Density 0.073%

    No Known Activations